DeepHalo: A Neural Choice Model with Controllable Context Effects

2026-01-08

arXiv.org

AI Summary

Human decision-making is often influenced by the composition of the choice set—a phenomenon known as context effects—yet existing models struggle to flexibly capture and interpret interaction effects of varying orders while leveraging option-specific features. This work proposes DeepHalo, a novel neural choice model that explicitly disentangles and models first- and higher-order Halo effects through a controllable-order interaction module, all while incorporating option features. DeepHalo is the first method to enable order-wise decomposition of context effects within feature-based choice modeling, offering both interpretability and universal approximation capability—even in settings without features. Experiments demonstrate that DeepHalo achieves superior predictive performance on both synthetic and real-world datasets and clearly reveals the contribution of each order of context effects to choice behavior.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Game Theory and Economic Paradigms: Social Choice / Voting

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Fairness, privacy, and diversity in economic environments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself -- a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

Problem

• context effect
• Halo effect
• choice modeling
• feature-based interaction
• interpretability

Innovation

• context effects
• Halo effect
• neural choice model
• interaction order
• interpretable modeling